Estimating the standard deviation of a Normal distribution when the distribution's mean is unknown

Download a complete copy of this risk analysis resource for free here.


For a given set of data randomly sampled from a Normal distribution, whose mean m is unknown and unknown standard deviation s, the distribution of uncertainty of the true standard deviation is calculated from the formula:

                

where  is a chi-squared distribution with n-1 degrees of freedom. It has a mean of (n-1) so the term in the square root is centred on 1, which means that the uncertainty distribution for s is centred around .

[This page provides an explanation of the derivation]

This spreadsheet example model lets you generate values for the above uncertainty distribution for s for a data set.